© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6023
    Prev
    Next
    INDEX
    Explanations

    sections of documents with proper nouns and industry terminology.

    oai_token-act-pair · gemini-2.0-flash

    Field

    np_max-act · gemini-2.0-flash

    ▁Field

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regiment
    -0.99
     AssemblyProduct
    -0.96
    contentLoaded
    -0.93
     Hemisphere
    -0.92
    Personensuche
    -0.90
     Repository
    -0.86
     Watershed
    -0.85
    __(/*!
    -0.85
     Estuary
    -0.85
     Raceway
    -0.85
    POSITIVE LOGITS
    ↵↵
    0.66
     space
    0.65
     central
    0.60
     community
    0.59
     structure
    0.54
     infrastructure
    0.53
     branch
    0.52
     area
    0.51
     network
    0.49
     group
    0.49
    Activations Density 4.893%

    No Known Activations